INDEX

Explanations

phrases related to expectations and evaluations of people's actions or situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

raisal

-0.15

Â¬

-0.15

:↵↵

-0.14

isible

-0.14

ÄĲT

-0.13

 :↵↵

-0.13

’ÑĶ

-0.13

uppe

-0.12

-%

-0.12

cpp

-0.12

POSITIVE LOGITS

gether

0.21

bidden

0.20

oretical

0.19

bsites

0.19

jourd

0.17

tempts

0.17

itionally

0.17

arLayout

0.17

nger

0.16

theless

0.16

Activations Density 0.848%

phrases related to expectations and evaluations of people's actions or situations

No Comments

No Known Activations