INDEX

Explanations

specific nouns and their associated actions or statuses in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Äįel

-0.17

 stains

-0.15

ie

-0.15

ies

-0.15

iral

-0.14

gain

-0.14

_references

-0.14

Wed

-0.14

èĨ

-0.14

Äįer

-0.14

POSITIVE LOGITS

ardy

0.17

rire

0.17

rale

0.17

ifestyles

0.15

 Gilbert

0.14

aroo

0.14

ury

0.14

 Fury

0.14

errupted

0.14

Activations Density 0.049%

specific nouns and their associated actions or statuses in various contexts

No Comments

No Known Activations