INDEX

Explanations

fragmented words and symbols, likely related to encoding or formatting issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ð±Ð°Ð²

-0.16

#index

-0.15

\Carbon

-0.14

Te

-0.14

okies

-0.14

.addObserver

-0.14

conto

-0.13

ãĥĵãĥ¼

-0.13

.setProgress

-0.13

Te

-0.13

POSITIVE LOGITS

ÎºÎŃ

0.17

 high

0.16

high

0.16

 High

0.16

High

0.16

-high

0.15

 Pills

0.15

 dayan

0.15

 highs

0.15

ëł¬

0.14

Activations Density 0.006%

fragmented words and symbols, likely related to encoding or formatting issues

No Comments

No Known Activations