INDEX

Explanations

phrases that involve accusations or blame

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_echo

-0.15

_PATCH

-0.14

_vlog

-0.14

ebek

-0.14

lingen

-0.14

 promin

-0.14

ottage

-0.14

Ð»Ð°ÑĪ

-0.14

 strncmp

-0.14

ksam

-0.14

POSITIVE LOGITS

0.16

zug

0.15

 something

0.15

ru

0.15

 halves

0.15

 comp

0.14

chap

0.14

auses

0.14

to

0.14

Activations Density 0.021%

phrases that involve accusations or blame

No Comments

No Known Activations